Density estimation of grey-level co-occurrence matrices for image texture analysis

The Haralick texture features are common in the image analysis literature, partly because of their simplicity and because their values can be interpreted. It was recently observed that the Haralick texture features are very sensitive to the size of the GLCM that was used to compute them, which led to a new formulation that is invariant to the GLCM size. However, these new features still depend on the sample size used to compute the GLCM, i.e. the size of the input image region-of-interest (ROI). The purpose of this work was to investigate the performance of density estimation methods for approximating the GLCM and subsequently the corresponding invariant features. Three density estimation methods were evaluated, namely a piece-wise constant distribution, the Parzen-windows method, and the Gaussian mixture model. The methods were evaluated on 29 different image textures and 20 invariant Haralick texture features as well as a wide range of different ROI sizes. The results indicate that there are two types of features: those that have a clear minimum error for a particular GLCM size for each ROI size, and those whose error decreases monotonically with increased GLCM size. For the first type of features, the Gaussian mixture model gave the smallest errors, and in particular for small ROI sizes (less than about ). In conclusion, the Gaussian mixture model is the preferred method for the first type of features (in particular for small ROIs). For the second type of features, simply using a large GLCM size is preferred.

[1]  Kyle J. Lafata,et al.  An investigation of machine learning methods in delta-radiomics feature analysis , 2019, PloS one.

[2]  Christoph Kleinn,et al.  Ensemble classification of individual Pinus crowns from multispectral satellite imagery and airborne LiDAR , 2018, Int. J. Appl. Earth Obs. Geoinformation.

[3]  Johan Trygg,et al.  Haralick texture features from apparent diffusion coefficient (ADC) MRI images depend on imaging and pre-processing parameters , 2017, Scientific Reports.

[4]  P. Georg,et al.  Association between pathology and texture features of multi parametric MRI of the prostate , 2016, Physics in medicine and biology.

[5]  Richa Singh,et al.  Fingerprint sensor classification via Mélange of handcrafted features , 2016, 2016 23rd International Conference on Pattern Recognition (ICPR).

[6]  Prateek Prasanna,et al.  Co-occurrence of Local Anisotropic Gradient Orientations (CoLlAGe): A new radiomics descriptor , 2016, Scientific Reports.

[7]  Ruijiang Li,et al.  Intratumor partitioning and texture analysis of dynamic contrast‐enhanced (DCE)‐MRI identifies relevant tumor subregions to predict pathological response of breast cancer to neoadjuvant chemotherapy , 2016, Journal of magnetic resonance imaging : JMRI.

[8]  L. Schwartz,et al.  Defining a Radiomic Response Phenotype: A Pilot Study using targeted therapy in NSCLC , 2016, Scientific Reports.

[9]  A. Chattopadhyay,et al.  Cholesterol-dependent Conformational Plasticity in GPCR Dimers , 2016, Scientific Reports.

[10]  Sangram Ganguly,et al.  A theoretical analysis of Deep Neural Networks for texture classification , 2016, 2016 International Joint Conference on Neural Networks (IJCNN).

[11]  A. Trister,et al.  Assessing the scale of tumor heterogeneity by complete hierarchical segmentation of MRI , 2015, Physics in medicine and biology.

[12]  Gabriel Cristóbal,et al.  Automated pollen identification using microscopic imaging and texture analysis. , 2015, Micron.

[13]  Mawia A. Hassan,et al.  Classification of Breast Tissue as Normal or Abnormal Based on Texture Analysis of Digital Mammogram , 2014 .

[14]  Peter Gibbs,et al.  Texture analysis in assessment and prediction of chemotherapy response in breast cancer , 2013, Journal of magnetic resonance imaging : JMRI.

[15]  Axel Wismüller,et al.  Classification of Small Lesions in Breast MRI: Evaluating The Role of Dynamically Extracted Texture Features Through Feature Selection. , 2013, Journal of medical and biological engineering.

[16]  Axel Wismüller,et al.  Classification of small lesions in dynamic breast MRI: eliminating the need for precise lesion segmentation through spatio-temporal analysis of contrast enhancement , 2012, Machine Vision and Applications.

[17]  D. Thomazini,et al.  Classification of polymers insulators hydrophobicity basead on digital image processing , 2012 .

[18]  Mislav Grgic,et al.  Breast Density Classification Using Multiple Feature Selection , 2012 .

[19]  Hervé Saint-Jalmes,et al.  Can Dynamic Contrast-Enhanced Magnetic Resonance Imaging Combined with Texture Analysis Differentiate Malignant Glioneuronal Tumors from Other Glioblastoma? , 2011, Neurology research international.

[20]  A. Villers,et al.  Prostate cancer characterization on MR images using fractal features. , 2010, Medical physics.

[21]  Siegfried Trattnig,et al.  Texture‐based classification of focal liver lesions on MRI at 3.0 Tesla: A feasibility study in cysts and hemangiomas , 2010, Journal of magnetic resonance imaging : JMRI.

[22]  Dawit Assefa,et al.  Robust texture features for response monitoring of glioblastoma multiforme on T1-weighted and T2-FLAIR MR images: a preliminary investigation in terms of identification and segmentation. , 2010, Medical physics.

[23]  Christos Davatzikos,et al.  Classification of brain tumor type and grade using MRI texture and shape in a machine learning scheme , 2009, Magnetic resonance in medicine.

[24]  Pantelis Georgiadis,et al.  Enhancing the discrimination accuracy between metastases, gliomas and meningiomas on brain MRI by volumetric textural features and ensemble pattern recognition methods. , 2009, Magnetic resonance imaging.

[25]  Hon J. Yu,et al.  Quantitative analysis of lesion morphology and texture features for diagnostic prediction in breast MRI. , 2008, Academic radiology.

[26]  Akinobu Shimizu,et al.  Medical image analysis of 3D CT images based on extension of Haralick texture features , 2008, Comput. Medical Imaging Graph..

[27]  M. Giger,et al.  Volumetric texture analysis of breast lesions on contrast‐enhanced magnetic resonance images , 2007, Magnetic resonance in medicine.

[28]  Janez Demsar,et al.  Statistical Comparisons of Classifiers over Multiple Data Sets , 2006, J. Mach. Learn. Res..

[29]  Suyash P. Awate,et al.  Adaptive, nonparametric markov models and information-theoretic methods for image restoration and segmentation , 2006 .

[30]  Gerhard Weikum,et al.  Untersuchungen zur automatischen Klassifikation von Lamellengraphit mit Hilfe des Stützvektorverfahrens , 2005 .

[31]  Hamid Soltanian-Zadeh,et al.  Comparison of multiwavelet, wavelet, Haralick, and shape features for microcalcification classification in mammograms , 2004, Pattern Recognit..

[32]  G. Weikum,et al.  Examinations on the Automatic Classification of Lamellar Graphite Using the Support Vector Machine , 2004 .

[33]  Eric R. Ziegel,et al.  The Elements of Statistical Learning , 2003, Technometrics.

[34]  Robert Tibshirani,et al.  The Elements of Statistical Learning: Data Mining, Inference, and Prediction, 2nd Edition , 2001, Springer Series in Statistics.

[35]  T. Tokola,et al.  The forest stand margin area in the interpretation of growing stock using Landsat TM imagery , 1999 .

[36]  Yoshua Bengio,et al.  Gradient-based learning applied to document recognition , 1998, Proc. IEEE.

[37]  Paul Scheunders,et al.  Wavelets for texture analysis, an overview , 1997 .

[38]  N. Petrick,et al.  Computer-aided classification of mammographic masses and normal tissue: linear discriminant analysis in texture feature space. , 1995, Physics in medicine and biology.

[39]  Matti Pietikäinen,et al.  Performance evaluation of texture measures with classification based on Kullback discrimination of distributions , 1994, Proceedings of 12th International Conference on Pattern Recognition.

[40]  F. Ulaby,et al.  Textural Infornation in SAR Images , 1986, IEEE Transactions on Geoscience and Remote Sensing.

[41]  S. M. Collins,et al.  Range- and azimuth-dependent variability of image texture in two-dimensional echocardiograms. , 1983, Circulation.

[42]  R. N. Macsween,et al.  Computer analysis of ultrasonic signals in diffuse liver disease. , 1979, Ultrasound in medicine & biology.

[43]  Robert M. Haralick,et al.  Textural Features for Image Classification , 1973, IEEE Trans. Syst. Man Cybern..

[44]  E. Parzen.  On Estimation of a Probability Density Function and Mode , 1962 .